Dref360

"""Good example"""
def random_shift(x, wrg, hrg, row_axis=1, col_axis=2, channel_axis=0,
                 fill_mode='nearest', cval=0., tx=None, ty=None):
    """Performs a random spatial shift of a Numpy image tensor.
    # Arguments
        x: Input tensor. Must be 3D.
        wrg: Width shift range, as a float fraction of the width.
        hrg: Height shift range, as a float fraction of the height.
        row_axis: Index of axis for rows in the input tensor.
        col_axis: Index of axis for columns in the input tensor.

Dref360

import os
from collections import defaultdict

import h5py
import numpy as np

pjoin = os.path.join


def convert_multi_to_single(multipath, fp):

Dref360

import cv2
import numpy as np
from keras.preprocessing.image import ImageDataGenerator
from keras.utils import Sequence


class MySequence(Sequence):
    def __init__(self):
        self.path = '~/Images/cat.jpg'
        self.imgaug = ImageDataGenerator(rotation_range=20,

Dref360

import keras.backend as K
import tensorflow as tf
from tensorflow.keras.layers import Layer

"""Not tested, I'll play around with GANs soon with it."""
from tensorflow.keras.layers import Conv2D
import numpy as np


class CoordConv2D(Layer):

Dref360

#!/usr/bin/env python
import subprocess
import sys

def get_staged():
    proc = subprocess.Popen(['git', 'diff', '--name-only', '--cached'], stdout=subprocess.PIPE)
    staged_files = proc.stdout.readlines()
    staged_files = [f.decode('utf-8') for f in staged_files]
    staged_files = [f.strip() for f in staged_files]
    staged_files = [f for f in staged_files if f.endswith('.py')]

Dref360

import gc
import os
import shutil
import tracemalloc
from pathlib import Path

import numpy as np

from keras import backend as K
from keras import callbacks

Dref360

from typing import Optional

import numpy as np
import torch
from torch.utils.data import DataLoader, TensorDataset

from baal.active import ActiveLearningDataset


class AlternateIterator:

Dref360

import numpy as np
import torch
from ignite.engine import Engine, Events, create_supervised_trainer
from pydantic import BaseModel
from torch.utils.data import DataLoader
from torchvision.datasets import CIFAR10
from torchvision.models import vgg16
from torchvision.transforms import transforms
from tqdm import tqdm

Dref360

FROM python:3.7

WORKDIR /tmp
COPY requirements.txt .

RUN pip install --no-cache \
                -r requirements.txt \
                uwsgi==2.0.19.1 \
                supervisor==4.2.2 \
                label-studio==1.0.2 \

Dref360

The code should run as is with the following dependencies:

pip install transformers datasets baal matplotlib tqdm